Health Medical Homework Help

Introduction

A research question essentially guides every research. A well-formulated research question isolates the purpose and the research problem by providing a clear relationship between variables and the hypothesis being tested (Laureate, 2012). While there are various types of research questions (i.e., descriptive, exploratory, explanatory, or experimental), all research questions can be answered using either primary or secondary data (Daniel, 2019; Walden, n.d; Laureate, 2012. All research questions should also align the variables selected with an appropriate research design and suitable statistical test (Laureate, 2012). The purpose of this is to formulate a research question relevant to the dataset, select and justify variables. The variables used for this discussion were derived from the PUBH 8500 Week01 Dataset (Walden, n.d.).

Research Question

The number one aim of this discussion is to formulate a research question from an existing dataset. From an epidemiologic perspective, I chose to explore the relationship between exposure and disease and based on the variables provided, a research question can be formulated to determine if stroke (disease) occurs as much among people having hypertension as it does among people without hypertension. A common analysis in epidemiology for dichotomous variables is the use of a contingency (2×2) table (Daniel, 2019; Walden, n.d.). The research question allows for testing the relationship between variables categorized based on their exposure to some disease risk factor (Forthofer; 2007; Walden, n.d.). The research question (RQ) is stated below:

RQ: To what extent is there a relationship between hypertension and stroke?

Hypotheses

Null Hypothesis (H0): Is there a significant relationship between hypertension and stroke

Alternative Hypothesis (HA): There is a significant relationship between hypertension and stroke.

Dependent and Independent Variables & Coding

Two dichotomous (categorical) variables, hypertension, and stroke were selected from the PUBH 8500 Week01 dataset to test the relationship between hypertension and stroke (Walden, n.d.). Both variables were selected based on general theories, previously tested hypotheses, and documented empirical and clinical evidence on the relationship between exposure (risk factor) and disease (outcome) (Daniel, 2019; Walden, n.d.). The layout of the linkages between the dependent and independent variables and the hypotheses tested are shown below:

Independent Variables (IV):

IV₁= Hypertension 0=No for had hypertension, 1=Yes for had hypertension

Dependent Variables (DV):

DV=Stroke 0=No for had stroke, 1=Yes for had stroke

Chi-Square or t-test to Analyze the Data

Chi-Square and t-test are parametric tests used for the hypothesis test. The t-test is used for comparing the means of two groups. At the same time, Chi-Square is a test of association, used to either assess relationships between categorical groups by either making comparisons between observed versus other known distributions (Forthofer, 2007; Walden, n.d.).. Based on the research question, the variable types, and the levels of measurements, the appropriate statistical procedure test to perform such an analysis is the Chi-Square (Daniel, 2019; Walden, n.d.). The chi-Square statistic is commonly used for testing relationships between nominal and ordinal data (categorical variables) (Daniel, 2019; Walden, n.d.). A chi-Square statistic is inferential statistics for testing relationships between categorical variables, testing whether there is a relationship between two variables. Unlike a t-Test, a Chi-Square test does provide the direction or the extent of the relationship. (Forthofer, 2007; Walden, n.d.).

Crosstabulation presents the distributions of two categorical variables simultaneously, with the intersections of the categories of the variables appearing in the cells of the table (Forthofer, 2007; Walden, n.d.). The Chi-Square Test of Independence assesses whether an association exists between the two variables by comparing the observed pattern of responses in the cells to the way that would be expected if the variables were truly independent of each other (Daniel, 2019; Walden, n.d.). Since the data provided is a secondary data set, the research question determines the types of variables to use and the appropriate statistical analysis for the described variables(Laureate, 2012). A Chi-Square test using a 2×2 contingency table would also be helpful, in this scenario to test the relational hypotheses between hypertension and stroke and to determine if they are significantly different from those who have a or have no stroke.

Conclusion

A well-formulated research question is vital for guiding research projects and provides a clear focus and purpose for the researcher and the reader. A data-driven research question can be used on an identified social problem and or a gap in the literature (Laureate, 2012). For this discussion, I explored the methods of formulating a research question from two categorical variables (hypertension and stroke). The discussion also covers the use of chi-square for testing the null hypothesis about the relationship between hypertension and stroke, to determine whether those having hypertension (exposure) have more illness (stroke) than those not exposed, by performing a test of the association between exposure and disease in the two groups. A Chi-Square is derived from a contingency table (2×2) table, which provides the overall distribution of people having (exposure) hypertension and disease (stroke).

References

Daniel, W. W. & Cross, C. L. (2019). Biostatistics: A foundation for analysis in the health sciences (11th ed.). Wiley.

Forthofer, R. N., Lee, E. S., & Hernandez, M. (2007). Biostatistics: A guide to design, analysis, and discovery. Amsterdam, Netherlands: lsevier Academic Press

Laureate Education, Inc. (Executive Producer). (2012). Biostatistics basics. Baltimore, MD: Author.

Walden University. (n.d.). Week 1 Summary Review & Quiz 1 Study Guide [Handout]. Walden university blackboard. Https://class.waldenu.edu

Walden University. (n.d.). Chi-Square Test [Handout]. Walden university blackboard. Https://class.waldenu.edu

Walden University. (n.d.). t- Test [Handout]. Walden university blackboard. Https://class.waldenu.edu

Walden University. (n.d.). PUBH 8500 Week01 dataset [dataset]. Walden university blackboard. Https://class.waldenu.edu

3 days ago

Carlin Nelson

RE: Discussion 1 – Week 1

COLLAPSE